Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Triple loss-based improved neural network pedestrian re-identification method

A pedestrian re-recognition, neural network technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve problems such as poor portability, unstable shape, and inability to apply to multiple scenarios, and achieve high recognition accuracy. rate, the effect of ensuring robustness

Active Publication Date: 2017-05-31
CHINACCS INFORMATION IND
View PDF3 Cites 60 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the changeable posture of the human body, the shape is not fixed, and the color characteristics are different with the change of clothing, it is still a very challenging subject. However, due to its wide application prospects, although the task of pedestrian detection is facing many difficulties, still attracts the attention of many researchers
[0003] Most of the current pedestrian recognition methods use softmax regression to converge the convolutional neural network and generate a model for people classification. However, when the picture scene changes greatly, the robustness cannot be guaranteed, and it cannot be applied to multiple scenes (ie Figures with a fixed background, poor portability)

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Triple loss-based improved neural network pedestrian re-identification method
  • Triple loss-based improved neural network pedestrian re-identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The following examples are used to describe the implementation of the present invention in detail, so as to fully understand and implement the process of how to apply technical means to solve technical problems and achieve technical effects in the present invention.

[0020] The present invention provides an improved neural network pedestrian re-identification method based on triple loss, which specifically includes the following steps:

[0021] Step S1: Construct a sample database, and expand the number of each sample picture in the sample database, from the original one sample picture to eight sample pictures to form a small data set; specifically, one sample picture is separately Translation in four directions: upper left, upper right, lower left, and lower right, the scale of translation is: y=height×(±0.5), x=width×(±0.5); along the center of the sample picture, press counterclockwise and clockwise respectively Rotate 5°; mirror the sample picture, through the abov...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a triple loss-based improved neural network pedestrian re-identification method. The method comprises the following steps of constructing a sample database, establishing positive and negative sample libraries based on the sample database, and randomly selecting two positive samples and one negative sample to form a triple; constructing a triple loss-based neural network, and performing training, wherein the neural network is formed by connecting three parallel convolution neural networks with a triple loss layer; inputting a to-be-tested picture and each sample picture in the expanded sample database, which serve as a group of inputs, to the trained neural network in sequence, wherein another input of the neural network is zero or zero input; and calculating a distance of eigenvectors of two input pictures output by the neural network by utilizing a Euclidean distance, and querying and arranging first 20 Euclidean distances in an ascending order, and then performing simple manual screening to obtain a final identification result. The method has the beneficial effects that the identification method can be suitable for a picture scene with a relatively great change, can ensure robustness, and has relatively high identification accuracy.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to an improved neural network pedestrian re-identification method based on triple loss. Background technique [0002] With the advancement of technology, smart devices such as computers are more and more widely used in people's daily life. Computers are more efficient and accurate than humans in handling repetitive and data-intensive tasks. Naturally, people hope that computers can deal with some more intelligent problems like humans. Computer vision is an important part in the new application field of computer. It is the core and the most extensive application of computer vision to replace or assist humans to complete the detection and tracking of targets. From fingerprints or faces used in daily life From unlocking, to automatic driving of cars, robot control, etc. are all closely related to computer vision technology. Human beings are the main body of social life, and...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/161G06V40/103G06F18/22G06F18/214
Inventor 舒泓新蔡晓东陈昀
Owner CHINACCS INFORMATION IND
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products